Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5184
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to language and linguistic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯Ńè¨Ģ
    -0.07
    è¨Ģèijī
    -0.07
    lashes
    -0.07
    ASSES
    -0.07
    eyn
    -0.07
    IFICATIONS
    -0.07
     prince
    -0.07
    edir
    -0.07
    maz
    -0.07
    eters
    -0.07
    POSITIVE LOGITS
     acquisition
    0.09
     Acquisition
    0.08
     learning
    0.08
     processing
    0.07
     teaching
    0.07
     Arts
    0.07
     rights
    0.07
    -te
    0.06
     arts
    0.06
     structure
    0.06
    Activations Density 0.010%

    No Known Activations